Recycling and Biomass Inuence on the Production-Based CO2 Intensity Based on Circular Economy Concept

9 In a closed loop structure, the circular economy reflects a concept for converting material and 10 energy wastes into capital for other purposes. The circular economy's key goal is to reduce energy 11 and material waste. The best-case scenario will be to eliminate wastes and repurpose them, which 12 is one of the key goals of the circular economy. The circular economy and sustainable development 13 are inextricably linked. The framework reflects resource reuse and recycling in order to reduce 14 waste and the use of biodegradable items that can be returned to the ecosystem after rejection. 15 Many programs are being developed to incorporate the circular economy in order to apply the 16 system's best practices. Recycling and reusing goods for the same or new items are the best 17 practices for reducing waste and energy consumption. The main goal of the study was to analyze 18 the effect of waste generation and recycling on production-based CO2 intensity based on circular 19 economy concept. For such a purpose adaptive neuro fuzzy inference system (ANFIS) was 20 implemented since the methodology is suitable for statistical investigation of strongly nonlinear 21 data sample due to features of fuzzy logic system. Generated and recycled waste including biomass 22 is the most influential factors for the production-based CO2 intensity based on circular economy 23 concept. The obtained results could represent the best practices for implementation of circular 24 economy concept. 25


30
The circular economy is a framework for long-term sustainability that aims to reduce 31 material and energy waste. Materials cycles are the central principle of the circular economy, 32 which aims to minimize negative environmental effects, reduce energy consumption, and promote 33 economic growth. The linear economy model has dominated industrial growth, resulting in 34 pollution and the overuse of scarce natural resources. Reusing, remanufacturing, restoring, and 35 updating goods or materials are all part of the circular economy. The circular economy in the 36 energy sector is focused on renewable energy sources such as solar, wind, biomass, and waste-37 derived energy. One of the most critical circular economy principles is the use of biodegradable 38 materials that can be returned to the atmosphere after being rejected, resulting in no waste.
In article [1] has been verified that the artificial neural network can bi applied in different 40 computational tasks in selected circular economy problems. Recycling and utilization of biomass 41 constituents have been verified ad the main factors in implementation of circular economy concept 42 [2]. Circular economy presents a new way of economic growth based on effective usage of energy 43 and material resources and environmental protection [3]. Results in article [4] have been shown 44 that in circular economy domain was made important contributions to research but these 45 contributions are heterogeneous with important differences and academic research does not fully 46 align with the policy agenda. Hence there is need for more comprehensive investigation of circular 47 economy parameters. It has been shown that the sustainable development in Industry 4.0 context 48 could contribute to circular economy [5,6]. Results in article [7] have been shows that there are hence there is need to develop a decision-making model based on the multivariable group, which 54 could facilitate decision and coordination between the different experts [8]. Results in article [9] 55 have been indicated that the circular economy could improve economic development and 56 ecological restoration as well. In article [10] has been shown important policy implications in 57 periodical shift from the traditional linear economy to a circular economy. The impact of circular 58 economy on economic growth has been investigated in article [11] and results have been shown 59 that the GDP growth rate decreases significantly but the economic decline gradually recovers as 60 time goes on. Results in article [12] have been shown a positive correlation between resources and 61 environmental performance with the driving factors for circular transformation being mainly GDP 62 and leading industries.

63
There are many initiatives in the works to incorporate circular economy best practices into 64 the scheme. Recycling and reusing goods for the same or different items are the best practices. The  Recycling rate is waste recycled as a percentage of all waste generated. Note that total 136 waste generated does not equal total waste managed due to stockpiled waste, which is counted in 137 the generation figures and will be included in the managed figures in the year it is sent to final 138 management.
TCO2e is tonnes of carbon dioxide equivalent, which is a measure that allows the In this study was used energy and non-energy material productivity parameters for CO2 created. The first set represent energy productivity parameters ( Table 2). The second set represent 172 non-energy productivity parameters (Table 3).    The following is a description of bell-shaped membership functions:: where Pi and Oi are known as the experimental and forecast values, respectively, and n is the total 276 number of checking data.

280
In the first stage ANFIS network is trained with data section in Table 1 where there are 281 four input variables and the output is TCO2e. The main goal is to determine RMS errors of each 282 single parameter from the Table 1 based on the TCO2e prediction. Figure 4 shows the RMSE 283 errors of the single parameters. One can note the generated waste has the smallest RMS error hence    Figure 6 shows the RMS errors of the combinations of two parameters for Scottish 310 Household waste. One can note the combination of generated and recycled wastes is the optimal 311 combination for the TCO2e prediction. Figure 7 shows the optimal combination with two inputs 312 and one output for the TCO2e prediction.   Based on the results for the OECD database energy intensity and biomass consumption is 328 the optimal combination (trn=0.0777, chk=0.2759) of two parameters with the highest impact on the 329 CO2 intensity in the OECD members. Therefore, biomass has the very high carbon impact and it 330 has to be recycled and reused in circular economy.

331
Three selected parameters are extracted and new ANFIS model is generated and trained 332 with 100 epochs. Figure 8 shows the ANFIS prediction of TCO2e index based on two selected 333 combinations. The all data are used for ANFIS training and checking as well. In other words,

334
ANFIS was trained with all data and then checking against the same data. There is high prediction

350
Since ecological and environmental sustainability are at the forefront of the economy, the 352 circular economy is the economy for the future. The circular economy's central concept is human 353 life's long-term viability. The circular economy may offer a way to overcome the current 354 production and consumption model, which is limited in terms of energy resources. This economy 355 is focused on a closed-loop system in which the primary energy and material resources are urban 356 and industrial wastes.

357
The main goal of the study was to analyze the effect of waste generation and recycling on 358 production-based CO2 intensity based on circular economy concept. For such a purpose adaptive 359 neuro fuzzy inference system (ANFIS) was implemented since the methodology is suitable for 360 statistical investigation of strongly nonlinear data sample. Generated and recycled waste including 361 biomass is the most influential factors for the production-based CO2 intensity based on circular 362 economy concept. The main concluding remarks could be summed as follows:

363
-Generated waste has high impact on the carbon dioxide emission,

364
-Biomass consumption has the high impact on the carbon dioxide emission, 365 366